Development of an Efficiency Platform Based on MQTT for UAV Controlling and DoS Attack Detection.

Area of Science:

• Computer Science
• Cybersecurity
• Robotics

Background:

• Unmanned Aerial Vehicles (UAVs) are increasingly integrated into Internet of Things (IoT) networks for applications like delivery and agriculture.
• The growing adoption of UAVs makes them vulnerable to cyberattacks, necessitating robust security measures.

Purpose of the Study:

• To develop an efficient platform for UAV control and Denial-of-Service (DoS) detection.
• To ensure secure communication within UAV systems and with the broker.

Main Methods:

• Implementation of a platform utilizing the Message Queuing Telemetry Transport (MQTT) protocol for UAV control.
• Integration of Denial-of-Service (DoS) detection mechanisms within the UAV system.
• Efficiency testing measuring latency, network/memory consumption, and payload-delay correlation across different Quality of Service (QoS) levels.
• Application of LightGBM with Bayesian optimization and data balancing on the AWID2 dataset for DoS detection.

Main Results:

• A strong positive correlation (>90%) was observed between data payload size and delay time across all QoS levels.
• The DoS detection model achieved a True Positive Rate (TPR) of 0.97 using 16 features.
• The developed platform demonstrated efficiency in UAV control and secured communications.

Conclusions:

• The proposed platform offers an efficient solution for UAV control and enhances communication security.
• The integrated DoS detection system provides effective protection against cyber threats in UAV networks.
• This research contributes to the secure and scalable deployment of UAVs in IoT environments.